Set up

library(ggplot2)
library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(plotly)
## 
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
## 
##     last_plot
## The following object is masked from 'package:stats':
## 
##     filter
## The following object is masked from 'package:graphics':
## 
##     layout
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ lubridate 1.9.3     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1
## ✔ readr     2.1.5
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ plotly::filter() masks dplyr::filter(), stats::filter()
## ✖ dplyr::lag()     masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
knitr::opts_chunk$set(
  fig.width = 6,
  fig.asp = .6,
  out.width = "90%"
)

theme_set(theme_minimal() + theme(legend.position = "bottom"))

options(
  ggplot2.continuous.colour = "viridis",
  ggplot2.continuous.fill = "viridis"
)

scale_colour_discrete = scale_colour_viridis_d
scale_fill_discrete = scale_fill_viridis_d

##Load Dataset

spotify_data = 
  read_csv("spotify_songs.csv") |> 
  mutate(popularity=track_popularity,
         genre=playlist_genre)
## Rows: 32833 Columns: 23
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): track_id, track_name, track_artist, track_album_id, track_album_na...
## dbl (13): track_popularity, danceability, energy, key, loudness, mode, speec...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

##Distrubution of dancebility

violin_danceability = spotify_data |> 
  plot_ly(
    x = ~genre,
    y = ~danceability,
    type = "violin",
    color= ~genre,
    box = list(visible = TRUE),          
    meanline = list(visible = TRUE)
  ) |> 
  layout(
    title = "Distribution of Danceability by Genre",
    xaxis = list(title = "Genre"),
    yaxis = list(title = "Danceability")
  )

violin_danceability

##Danceability and popularity

scatter_plot = spotify_data |> 
  plot_ly(
    x = ~danceability,
    y = ~popularity,
    color= ~genre,
    type = "scatter", 
    alpha=.2,
    text = ~paste("Genre: ", genre, "<br>Danceability: ", danceability, "<br>Popularity: ", popularity)
  ) |> 
  layout(
    title = "Danceability vs. Popularity",
    xaxis = list(title = "Danceability", range = c(0, 1)),
    yaxis = list(title = "Popularity", range = c(0, 100)),
    showlegend = FALSE
  )

scatter_plot
## No scatter mode specifed:
##   Setting the mode to markers
##   Read more about this attribute -> https://plotly.com/r/reference/#scatter-mode

Regression

model = lm(popularity ~ danceability, data = spotify_data)

scatter_plot = spotify_data |> 
  plot_ly(
    x = ~danceability,
    y = ~popularity,
    color = ~genre,
    type = "scatter", 
    alpha = 0.2,
    text = ~paste("Genre: ", genre, "<br>Danceability: ", danceability, "<br>Popularity: ", popularity)
  ) |> 
  add_trace(
    x = ~spotify_data$danceability,
    y = ~predict(model),
    mode = "lines",
    line = list(color = "red"),
    name = "Regression Line"
  ) |> 
  layout(
    title = "Danceability vs. Popularity",
    xaxis = list(title = "Danceability", range = c(0, 1)),
    yaxis = list(title = "Popularity", range = c(0, 100)),
    showlegend = FALSE
  )

scatter_plot
## No scatter mode specifed:
##   Setting the mode to markers
##   Read more about this attribute -> https://plotly.com/r/reference/#scatter-mode